PreprintCC BYbioRxiv
A comprehensive map of the sequence basis of transcription initiation in humans
- 1Stanford University
Abstract
Transcription initiation is a key marker of active enhancers and promoters. Here we describe an atlas of efficient and interpretable deep learning models trained on over 200 transcription initiation profiling experiments representing all major human organs and many cancer types. We show that our models accurately predict initiation patterns from local DNA sequence and decode their sequence determinants across diverse cellular contexts.
Related
- EPIC: An open community challenge for sequence-based prediction of transcription initiation in five non-model metazoans
- Structural basis for the CsrA-dependent modulation of translation initiation by an ancient regulatory protein.
- Survey of transcription initiation in the streamlined genomes of Paramecium
- Developmental dynamics of transcription initiation highlight promoter shifts as a multifaceted regulatory mechanism in barley
- Inference on paths of yeast transcription pre-initiation complex assembly by model-based analysis of altered occupancy profiles
BibTeX
@misc{he2026comprehensive,
title = {{A comprehensive map of the sequence basis of transcription initiation in humans}},
author = {A. Y. He and C. Tian and A. Kundaje},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.29.762743},
url = {https://www.biorxiv.org/content/10.64898/2026.10.29.762743v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - A comprehensive map of the sequence basis of transcription initiation in humans
AU - A. Y. He
AU - C. Tian
AU - A. Kundaje
PY - 2026
DA - 2026/10/29
PB - bioRxiv
DO - 10.64898/2026.10.29.762743
UR - https://www.biorxiv.org/content/10.64898/2026.10.29.762743v1
AB - Transcription initiation is a key marker of active enhancers and promoters. Here we describe an atlas of efficient and interpretable deep learning models trained on over 200 transcription initiation profiling experiments representing all major human organs and many cancer types. We show that our models accurately predict initiation patterns from local DNA sequence and decode their sequence determinants across diverse cellular contexts.
ER -